什么是 mAP 指标以及它是如何计算的? [英] What is the mAP metric and how is it calculated?

问题描述

在计算机视觉和物体检测中，常用的评价方法是mAP.它是什么以及它是如何计算的?

In computer vision and object detection, the common evaluation method is mAP. What is it and how is it calculated?

推荐答案

引自上述 Zisserman 论文 - 4.2 结果评估(第 11 页):

首先，重叠标准"被定义为大于 0.5 的交集与联合.(例如，如果预测框相对于真实框满足此标准，则将其视为检测).然后使用这种贪婪"方法在 GT 框和预测框之间进行匹配:

First an "overlap criterion" is defined as an intersection-over-union greater than 0.5. (e.g. if a predicted box satisfies this criterion with respect to a ground-truth box, it is considered a detection). Then a matching is made between the GT boxes and the predicted boxes using this "greedy" approach:

方法输出的检测结果被分配给地面实况对象按(递减)排序的顺序满足重叠标准信心输出.图像中同一物体的多次检测被认为是错误检测，例如5 检测单个物体计为1次正确检测和4次错误检测

Detections output by a method were assigned to ground truth objects satisfying the overlap criterion in order ranked by the (decreasing) confidence output. Multiple detections of the same object in an image were considered false detections e.g. 5 detections of a single object counted as 1 correct detection and 4 false detections

因此每个预测框要么是真阳性，要么是假阳性.每个ground-truth框都是True-Positive.没有正反面.

Hence each predicted box is either True-Positive or False-Positive. Each ground-truth box is True-Positive. There are no True-Negatives.

然后通过平均精度-召回曲线上的精度值来计算平均精度，其中召回率在 [0, 0.1, ..., 1] 范围内(例如 11 个精度值的平均值).更准确地说，我们考虑稍微修正的 PR 曲线，其中对于每个曲线点 (p, r)，如果存在不同的曲线点 (p', r') 使得 p' > p 且 r' >= r，我们用这些点的最大 p' 替换 p.

Then the average precision is computed by averaging the precision values on the precision-recall curve where the recall is in the range [0, 0.1, ..., 1] (e.g. average of 11 precision values). To be more precise, we consider a slightly corrected PR curve, where for each curve point (p, r), if there is a different curve point (p', r') such that p' > p and r' >= r, we replace p with maximum p' of those points.

我仍然不清楚的是，那些从未检测到的 GT 盒子做了什么(即使置信度为 0).这意味着某些召回值是精度-召回曲线永远不会达到的，这使得上面的平均精度计算未定义.

What is still unclear to me is what is done with those GT boxes that are never detected (even if the confidence is 0). This means that there are certain recall values that the precision-recall curve will never reach, and this makes the average precision computation above undefined.

简答:在召回率达不到的区域，精度下降到0.

Short answer: in the region where the recall is unreachable, the precision drops to 0.

解释这一点的一种方法是假设当置信度阈值接近 0 时，无限数量的预测边界框会在整个图像中亮起.然后精度立即变为 0(因为只有有限数量的 GT 框)并且召回率在这条平坦曲线上不断增长，直到我们达到 100%.

One way to explain this is to assume that when the threshold for the confidence approaches 0, an infinite number of predicted bounding boxes light up all over the image. The precision then immediately goes to 0 (since there is only a finite number of GT boxes) and the recall keeps growing on this flat curve until we reach 100%.

这篇关于什么是 mAP 指标以及它是如何计算的?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！